activity
20242026
collaborators

6 papers

cs.CL2026

LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging

Seungeon Lee, Soumi Das, Manish Gupta +1

Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for fine-tuning large language models. However, conventional LoRA adapters are typically trained for a sing…

cs.CL2026

In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations

Mohammad Aflah Khan, Mahsa Amani, Soumi Das +5

Agents based on Large Language Models (LLMs) are increasingly being deployed as interfaces to information on online platforms. These agents filter, prioritize, and synthesize infor…

cs.CV2026

A Deep Multi-Modal Method for Patient Wound Healing Assessment

Subba Reddy Oota, Vijay Rowtula, Shahid Mohammed +3

Hospitalization of patients is one of the major factors for high wound care costs. Most patients do not acquire a wound which needs immediate hospitalization. However, due to facto…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CL2025

Assess and Prompt: A Generative RL Framework for Improving Engagement in Online Mental Health Communities

Bhagesh Gaur, Karan Gupta, Aseem Srivastava +2

Online Mental Health Communities (OMHCs) provide crucial peer and expert support, yet many posts remain unanswered due to missing support attributes that signal the need for help.…

cs.CV2024

ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videos

Arpan Phukan, Manish Gupta, Asif Ekbal

Previous studies on question generation from videos have mostly focused on generating questions about common objects and attributes and hence are not entity-centric. In this work,…